\r \r

Grok Imagine Extended (xAI Image & Video Generation)\r

\r Generate images and videos from text prompts using the xAI API.\r \r

Image Generation\r

\r

python3 {baseDir}/scripts/generate_image.py --prompt "your image description" --filename "output.png"\r
```\r
\r
With options:\r
\r
```bash\r
python3 {baseDir}/scripts/generate_image.py --prompt "a cyberpunk city at night" --filename "city.png" --resolution 2k --aspect-ratio 16:9\r
```\r
\r
## Image Editing\r
\r
Single source image:\r
\r
```bash\r
python3 {baseDir}/scripts/generate_image.py --prompt "make it a watercolor painting" --filename "edited.png" -i "/path/to/source.jpg"\r
```\r
\r
Multiple source images (up to 3):\r
\r
```bash\r
python3 {baseDir}/scripts/generate_image.py --prompt "combine into one scene" --filename "combined.png" -i img1.png -i img2.png\r
```\r
\r
## Video Generation\r
\r
Text-to-video:\r
\r
```bash\r
python3 {baseDir}/scripts/generate_image.py --prompt "a cat walking through flowers" --filename "cat.mp4" --video --duration 5\r
```\r
\r
Image-to-video (animate a still):\r
\r
```bash\r
python3 {baseDir}/scripts/generate_image.py --prompt "add gentle camera zoom and wind" --filename "animated.mp4" --video -i photo.jpg --duration 5\r
```\r
\r
## Models\r
\r
| Model | Type | Cost |\r
|-------|------|------|\r
| `grok-imagine-image` | Image (default) | $0.02/img |\r
| `grok-imagine-image-pro` | Image (high quality) | $0.07/img |\r
| `grok-imagine-video` | Video (auto for --video) | $0.05/sec |\r
\r
Select model with `--model grok-imagine-image-pro`. Video mode always uses `grok-imagine-video`.\r
\r
## All Options\r
\r
| Flag | Description |\r
|------|-------------|\r
| `--prompt`, `-p` | Text description (required) |\r
| `--filename`, `-f` | Output path (required) |\r
| `-i` | Input image for editing/animation (repeatable, max 3 for images, 1 for video) |\r
| `--model`, `-m` | Image model (default: grok-imagine-image) |\r
| `--aspect-ratio`, `-a` | 1:1, 16:9, 9:16, 4:3, 3:4, etc. |\r
| `--resolution`, `-r` | Image: 1k/2k. Video: 480p/720p |\r
| `--n` | Number of images 1-10 (default 1) |\r
| `--video` | Generate video instead of image |\r
| `--duration`, `-d` | Video duration 1-15 seconds (default 5) |\r
| `--api-key`, `-k` | Override XAI_API_KEY |\r
\r
## API Key\r
\r
- `XAI_API_KEY` env var\r
- Or set `skills."grok-imagine".apiKey` / `skills."grok-imagine".env.XAI_API_KEY` in `~/.openclaw/openclaw.json`\r
- Or auto-read from `~/keys.txt`\r
\r
## Notes\r
\r
- Use timestamps in filenames: `2026-03-01-cyberpunk-city.png`\r
- The script prints a `MEDIA:` line for OpenClaw to auto-attach on supported chat providers\r
- Do not read the image back; report the saved path only\r
- Image URLs from xAI are temporary; the script downloads them immediately\r
- Video generation is async and polls until done (can take 1-5 minutes)\r
- 2k resolution returns PNG; 1k returns JPEG\r